sf-b2b-apex
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of external data to influence the agent's output, creating a potential surface for indirect prompt injection.
- Ingestion points: The skill instructs the agent to use
WebSearchandWebFetchto retrieve live documentation from official Salesforce developer sites (developer.salesforce.com). - Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are defined for the fetched documentation content.
- Capability inventory: The skill utilizes
Write,Edit, andBashtools to modify files and execute local commands based on the technical context retrieved. - Sanitization: The skill lacks mechanisms to sanitize or validate the external content before it is processed by the agent to generate Apex code.
Audit Metadata